SS-SFDA：危险环境下道路分割的自监督无源域自适应
SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments
AI总结：
针对恶劣天气下的无监督道路分割问题，提出基于自监督学习的无源域自适应算法SS-SFDA，结合伪标签在线生成、自注意力等多种技术，在6个数据集上性能超现有方法至少10.26%，训练时间大幅缩短。
摘要：
我们提出了一种针对雨、雾等恶劣天气条件下无监督道路分割的新方法，包括一种基于自监督学习的无源域自适应（SFDA）新算法。此外，我们的方法采用多种技术解决SFDA中的各类挑战并提升性能，包括伪标签在线生成、自注意力机制，以及课程学习、熵最小化和模型蒸馏的应用。我们在对应真实和合成恶劣天气条件的6个数据集上评估了性能，该方法在无监督道路分割和SFDA任务上比所有现有工作至少高出10.26%，训练时间缩短18-180倍，且自监督算法的mIOU精度与现有有监督方法相当。
英文摘要：
We present a novel approach for unsupervised road segmentation in adverse weather conditions such as rain or fog. This includes a new algorithm for source-free domain adaptation (SFDA) using self-supervised learning. Moreover, our approach uses several techniques to address various challenges in SFDA and improve performance, including online generation of pseudo-labels and self-attention as well as use of curriculum learning, entropy minimization and model distillation. We have evaluated the performance on $6$ datasets corresponding to real and synthetic adverse weather conditions. Our method outperforms all prior works on unsupervised road segmentation and SFDA by at least 10.26%, and improves the training time by 18-180x. Moreover, our self-supervised algorithm exhibits similar accuracy performance in terms of mIOU score as compared to prior supervised methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
